First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
3
Score
70/100
Findings (3)
Detects fetching external URLs and using the content as agent instructions or rules
fetch combined template rules Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.
Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.
Detects loading of prompt templates or agent instructions from remote URLs at runtime
fetch combined template rules from `http Avoid loading and running third-party plugins or extensions at runtime without integrity verification. Implement code signing, checksum verification, and sandboxing for dynamically loaded code.
Likely FP if the third-party content is a well-known, established plugin loaded from a verified marketplace with code signing.
Detects URLs fetched at runtime that control or influence agent behavior without pinning
fetch combined template rules from `https:// + rules Avoid loading configuration or behavior-controlling content from runtime URLs. Bundle required configurations locally or pin remote config to versioned, integrity-verified endpoints.
Likely FP if the URL in the match is a documentation link or example URL (e.g., example.com) rather than an actual runtime-fetched configuration endpoint.